Triple
T22225632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yamato Sanzan |
E549330
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Mount Unebi |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mount Unebi | Statement: [Yamato Sanzan, hasPart, Mount Unebi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Unebi Context triple: [Yamato Sanzan, hasPart, Mount Unebi]
-
A.
Mount Unebi
chosen
Mount Unebi is a small, historically significant hill in Kashihara, Nara Prefecture, traditionally associated with Japan’s first emperor and early imperial mythology.
-
B.
Mount Erice
Mount Erice is a prominent mountain in western Sicily, Italy, known for its medieval hilltop town of Erice and panoramic views over the surrounding coast and islands.
-
C.
Mount Usu
Mount Usu is an active stratovolcano in Hokkaido, Japan, known for its frequent eruptions and dramatic impact on the surrounding landscape.
-
D.
Mount Heha
Mount Heha is the tallest mountain in Burundi, located in the Burundi Highlands near the city of Bujumbura.
-
E.
Mount Haruna
Mount Haruna is an active stratovolcano in Gunma Prefecture, Japan, known for its scenic caldera lake, hot springs, and popular hiking and sightseeing spots.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bee8de8819091ec5d14ea057f9e |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:37 p.m.